Havuz
Takip ettiğimiz konularda yükselen açık kaynak projeler — yıldız ivmesi, gerçek geliştirme aktivitesi ve AI değerlendirmesiyle.
Yalnız hareketli, son 28 günde commit almamış repoları gizler (yıldızı olan ama bırakılmış projeler). Commit sayısı henüz ölçülmemiş repolar da gizlenir.
EtiketTüm GitHub etiketleri — repo sahiplerinin koyduğu topic'lergöster
Etiketler yükleniyor…
- 1
The ultimate harness for coding agents and beyond. All your agents. All your machines. One command center. Start with code, then follow your
15,4/gün ort. +7 son gün +5,7 son 7g 1.661 commit 7 yazar TypeScript 04 Ağu 2026 güncellendi bugün - 2
A robot-painting benchmark for multimodal language models: reference images, text prompts, and custom goals. Built on AgentArk.
2,9/gün ort. +0 son gün +5 son 7g 30 commit 1 yazar Jupyter Notebook 18 Eki 2026 güncellendi 8 gün önce - 3
The first exam for code agents in the physical world: frozen robot tasks from many benchmark suites, each answered with a program and verifi
4,9/gün ort. +1 son gün +3,3 son 7g 104 commit 7 yazar Python 18 Eyl 2026 güncellendi bugün - 4
Official repository for RoboDojo
6,8/gün ort. +2 son gün +2,9 son 7g 3 commit 2 yazar Python 07 Tem 2026 güncellendi 6 gün önce - 5
Open source evals for physical AI. Run any LLM/VLA on any arm/humanoid against any real/sim benchmark.
5,6/gün ort. +5 son gün +2,3 son 7g 21 commit 12 yazar Python 26 Haz 2026 güncellendi dün - 6
Ten frontier VLM agents, five robotic capabilities, 1,000 cases. GeoProbe and traceable analyses of geometry, spatial reasoning, affordance,
0,5/gün ort. +4 son gün +1,7 son 3g — commit Python 28 Eyl 2026 güncellendi dün - 7
Official code for ForesightSafety-VLA (IROS 2026): a unified diagnostic safety benchmark for vision-language-action models on RoboTwin
12,4/gün ort. +0 son gün +1,2 son 5g 1 commit 1 yazar Python 29 Eki 2026 güncellendi 7 gün önce - 8
A robot-oriented full-stack framework for long-horizon embodied agents in evolving physical and social environments.
1,9/gün ort. +1 son gün +0,9 son 7g — commit Python 21 Eki 2026 güncellendi 10 gün önce - 9
Physical AI skills for coding agents, with field-tested robotics guidance, the robium-ai CLI, and a learning engine.
1,1/gün ort. +1 son gün +0,7 son 7g — commit JavaScript 03 Ağu 2026 güncellendi 29 gün önce - 10
Benchmarking Coding Agents for Interactive World Modeling from Embodied Videos - Rethinking Embodied Real2Sim from a Software Engineering Pe
7/gün ort. -7 son gün +0,6 son 7g 6 commit 2 yazar Python 05 Eki 2026 güncellendi bugün - 11
A unified framework for training, fine-tuning, and evaluating World Action Models
5,7/gün ort. -1 son gün +0,4 son 7g 18 commit 1 yazar Python 26 Ağu 2026 güncellendi 8 gün önce - 12
ros2 topic hz for every topic at once, without subscribing. Rates, gaps and node liveness, intra-process included, on stock ROS 2 binaries.
0,4/gün ort. +0 son gün +0,4 son 7g — commit C++ 07 Tem 2026 güncellendi 3 gün önce - 13
Manipulation benchmarks test acting to change; EmbodiedLab tests acting to know. Given only an objective and the apparatus, a robot runs its
1,4/gün ort. +0 son gün +0,3 son 7g — commit Python 23 Eki 2026 güncellendi 9 gün önce - 14
Engineering-grade ROS 1 / ROS 2 skill for Codex, Claude Code, and Gemini CLI.
0,3/gün ort. +1 son gün +0,1 son 7g — commit Python 09 Mar 2026 güncellendi 09 Mar 2026 - 15
NarrowWide: A LiDAR-inertial dataset with repeated transitions between confined and open spaces (IEEE T-FR 2026)
0,8/gün ort. +0 son gün +0,1 son 7g — commit 05 Eki 2026 güncellendi 29 gün önce - 16
Color-coded terminal output for ROS 2 — group nodes by color, highlight crashes and tracebacks, zero changes to your launch files or workflo
0,1/gün ort. +0 son gün +0,1 son 7g — commit Python 25 May 2026 güncellendi dün - 17
Persistent, local memory for developers and their coding agents. Records commands, output, errors, and the fixes that worked into SQLite and
1/gün ort. +0 son gün +0 son 7g 63 commit 4 yazar Rust 17 Haz 2026 güncellendi bugün - 18
FastCrest Tether: the OSS edge-to-cloud AI deploy CLI. Optimize, verify, deploy across Jetson, RTX, Apple Silicon, AMD. Hybrid edge-cloud in
0,4/gün ort. +0 son gün +0 son 7g — commit Python 13 Nis 2026 güncellendi 4 gün önce - 19
Scan your ROS2 workspace and visualize node topology as an interactive graph. No running system needed.
0,2/gün ort. +0 son gün +0 son 7g — commit Python 04 Nis 2026 güncellendi 28 Nis 2026 - 20
fastfetch for ROS2 — distro info, live nodes, workspaces, web dashboard. One command. Everything you need.
0,2/gün ort. +0 son gün +0 son 7g — commit Python 09 Mar 2026 güncellendi 9 gün önce - 21
An auditable and reproducible evaluation suite for LeWM-compatible latent world models, with official-compatible and difficulty-controlled p
0,4/gün ort. +0 son gün +0 son 7g — commit Python 21 Tem 2026 güncellendi 14 Eyl 2026 - 22
Self-hosted research intelligence for collecting, deduplicating, ranking, searching, and browsing the researchers, topics, and sources you c
0,5/gün ort. +0 son gün +0 son 7g — commit Python 16 Ağu 2026 güncellendi 21 Ağu 2026 - 23
A reproducible benchmark for bimanual manipulation in simulation and the real world.
0,2/gün ort. +0 son gün +0 son 7g — commit Python 13 Haz 2026 güncellendi 2 gün önce - 24
Your daily AI intelligence dispatch to Email 📧· Robotics, Agents & LLMs analyzed by Claude Opus · 每日多源聚合 + 深度分析，GitHub Actions 一键部署，无需服务器
0,1/gün ort. +0 son gün +0 son 7g — commit Python 29 May 2026 güncellendi 05 Ağu 2026 - 25
A self-hosted AI brain for the Vector robot by Anky Labs
0,1/gün ort. +0 son gün +0 son 7g — commit Python 16 May 2026 güncellendi 11 Haz 2026 - 26
Static ROS 2 architecture analysis, visualization, auditing, and CI policy enforcement for Python and C++ workspaces.
0,1/gün ort. +0 son gün +0 son 7g — commit Python 12 Haz 2026 güncellendi 4 gün önce - 27
Shows which Fast DDS transport (UDPv4 / SHM / data-sharing) each ROS 2 Jazzy topic uses, and why
0,2/gün ort. +0 son gün +0 son 7g — commit C++ 04 Eyl 2026 güncellendi 04 Eki 2026 - 28
A temporal visual reasoning benchmark over egocentric robot manipulation video — 39 scenarios, 7 dimensions, 34,713 questions
0,2/gün ort. +0 son gün +0 son 7g — commit Python 09 Eyl 2026 güncellendi 28 Eyl 2026 - 29
A measurement-grounded benchmark for evaluating physical fidelity in physics engines and video world models.
0,2/gün ort. +0 son gün +0 son 7g — commit 21 Ağu 2026 güncellendi 24 Ağu 2026 - 30
Open browser arena for embodied / VLA stacking benchmarks
0,2/gün ort. +0 son gün +0 son 7g — commit TypeScript 18 Ağu 2026 güncellendi 26 gün önce